Quantum-Behaved Particle Swarm Optimization with Weighted Mean Personal Best Position and Adaptive Local Attractor

Abstract

Motivated by concepts in quantum mechanics and particle swarm optimization (PSO), quantum-behaved particle swarm optimization (QPSO) was proposed as a variant of PSO with better global search ability. In this paper, a QPSO with weighted mean personal best position and adaptive local attractor (ALA-QPSO) is proposed to simultaneously enhance the search performance of QPSO and acquire good global optimal ability. In ALA-QPSO, the weighted mean personal best position is obtained by distinguishing the difference of the effect of the particles with different fitness, and the adaptive local attractor is calculated using the sum of squares of deviations of the particles’ fitness values as the coefficient of the linear combination of the particle best known position and the entire swarm’s best known position. The proposed ALA-QPSO algorithm is tested on twelve benchmark functions, and compared with the basic Artificial Bee Colony and the other four QPSO variants. Experimental results show that ALA-QPSO performs better than those compared method in all of the benchmark functions in terms of better global search capability and faster convergence rate.

Optimal Sizing of Battery-Integrated Hybrid Renewable Energy Sources with Ramp Rate Limitations on a Grid Using ALA-QPSO

“…This allows the particles to attain a global optimum. There have been several variants of QPSO as well [19][20][21]. An adaptive local attractor QPSO (ALA-QPSO) was proposed in [21] to enhance the search performance by introducing the weighted mean personal best of the particles.…”

“…In the original PSO, the position and velocity of the i-th particle in each iteration 'it' are updated according to Equation (16). As discussed in Section 1, the trajectory of these particles is influenced by an attractor [21].…”

“…Using the concept of particle trajectory, the principle of uncertainty from quantum mechanics is applied to generate a delta potential well that allows the particles to move across the entire search space. The position pos of the j-th dimension in the i-th particle is updated using the adaptive local attractor in each iteration according to Equation ( 17) [21]. The first term is updated based on the adaptive local attractor given in Equation (18), which is updated based on an adaptive contraction-expansion coefficient in Equation (19) and the diversity of the fitness of the population fit ij from the mean fitness fit mean in Equation (20).…”

“…The first term is updated based on the adaptive local attractor given in Equation (18), which is updated based on an adaptive contraction-expansion coefficient in Equation (19) and the diversity of the fitness of the population fit ij from the mean fitness fit mean in Equation (20). The second term in Equation ( 17) is updated according to the weighted mean personal best position of all the particles, as given in Equation (21).…”

“…The weighted mean personal best of each particle in the it-th iteration, mpbest(it), is given in Equation (21).…”